Unveiling the role of harmonization on clinically significant prostate cancer detection using MRI.
Authors
Affiliations (5)
Affiliations (5)
- LaTIM UMR1101, INSERM, University of Brest, Brest, France. [email protected].
- University Hospital of Brest, Brest, France. [email protected].
- LARIS, University of Angers, Angers, France.
- LaTIM UMR1101, INSERM, University of Brest, Brest, France.
- University Hospital of Brest, Brest, France.
Abstract
Accurate detection and classification of clinically significant prostate cancer remain critical challenges in medical imaging. Despite numerous studies focusing on feature extraction and classification, none have systematically assessed the impact of harmonization techniques on multicenter imaging data. This study aimed to improve diagnostic performance by integrating harmonization via unsupervised clustering with clinical variables into machine learning models, even when the source center is unknown. We extracted features from T2-weighted magnetic resonance images using two approaches: handcrafted radiomics and deep learning-based representations obtained via a 3D convolutional autoencoder architecture. To address inter-center variability, the data were harmonized using an unsupervised clustering approach that generated 19 distinct clusters, followed by ComBat harmonization. Machine learning classifiers were then trained with and without the inclusion of clinical variables (prostate-specific antigen levels and patient age). The models were evaluated using multiple metrics. Harmonization significantly improved classification performance. In particular, models based on 3D convolutional autoencoder-derived features achieved an accuracy of 75.33% and an area under the curve (AUC) of 0.74. The incorporation of clinical variables further enhanced model performance; the best model combining radiomics features with clinical data attained an accuracy of 77.67% and an AUC of 0.85. These performance metrics are concurrent with those reported in the literature for this challenge, demonstrating that our novel approach can effectively mitigate inter-center variability and enhance diagnostic accuracy. Our findings underscore the potential of harmonization via unsupervised clustering, combined with the inclusion of clinical variables, to significantly enhance the diagnostic performance of machine learning models for prostate cancer detection. This novel strategy not only addresses a gap in the current literature but also produces performance metrics comparable to those reported in multicenter studies, thereby supporting the development of robust, clinically applicable diagnostic tools.